Abstract
With the rise of multidimensional object learning, there has been increasing interest in tensor representations of data, which allows for the simultaneous modeling of information from multiple sources. In previous studies, the tensor representations of the data are largely restricted to treating the observed tensors as independent objects and have not explicitly accounted for potential temporal dependency among the tensors. This assumption substantially limits the applicability of tensor representations, since most multidimensional time-dependent processes, from crypto-assets to human brain signals, exhibit various types of serial dependency. Neglecting this dependence structure typically results in inflated false-positive rates, especially when the observed data samples are of moderate size, and also leads to underestimation of model uncertainty, which profoundly affects all aspects of risk analytics. To address this fundamental restriction, we propose a novel framework, named the WeDTLasso, for estimating the concentration matrix of a sequence of tensor-valued data, which allows us to explicitly and systematically account for the dependency between multiple information sources over time. We derive theoretical guarantees specifying the near-oracle error bound for WeDTLasso and assess its performance on simulated data, exhibiting various types of serial dependency. Furthermore, we illustrate utility of WeDTLasso in application to the portfolio construction for crypto-assets. We find that based on the Matthews Correlation Coefficient, WeDTLasso outperforms other state-of-the-art approaches with relative gains of up to 20%. Moreover, our findings suggest that our WeDTLasso estimator yields up to 50% increase in the Sharpe Ratio for portfolio selection performance, compared to state-of-the-art algorithms for portfolio analytics.
Dorcas Ofori-Boateng and Jaidev Goel are co-first authors with equal contribution and importance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Data, code, and system information has been provided for reproducibility in Appendix C of the Supplementary material.
References
Araujo, M., Ribeiro, P., Song, H.A., Faloutsos, C.: Tensorcast: forecasting and mining with coupled tensors. Knowl. Inf. Syst. 59, 497–522 (2019)
Bakry, W., Rashid, A., Al-Mohamad, S., El-Kanj, N.: Bitcoin and portfolio diversification: a portfolio optimization approach. J. Risk Financ. Manag. 14(7), 282 (2021). https://doi.org/10.3390/jrfm14070282
Besag, J.: Efficiency of pseudolikelihood estimation for simple gaussian fields. Biometrika 616–618 (1977)
Bickel, P.J., Ritov, Y., Tsybakov, A.B.: Simultaneous analysis of Lasso and Dantzig selector. Ann. Stat. 37(4), 1705–1732 (2009). http://www.jstor.org/stable/30243685
Bühlmann, P., Van De Geer, S.: Statistics for High-Dimensional Data: Methods, Theory and Applications. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-20192-9
Chicco, D., Jurman, G.: The advantages of the Matthews Correlation Coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics 21(1), 1–13 (2020)
Doukhan, P., Massart, P., Rio, E.: The functional central limit theorem for strongly mixing processes. Annales de l’I.H.P. Probabilités et statistiques 30(1), 63–82 (1994). http://eudml.org/doc/77475
Doukhan, P., Neumann, M.H.: Probability and moment inequalities for sums of weakly dependent random variables, with applications. Stochast. Process. Appl. 117(7), 878–903 (2007)
Feng, Y., Li, Q., Chen, D., Rangaswami, R.: Solartrader: enabling distributed solar energy trading in residential virtual power plants. In: Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, pp. 60–69 (2020)
Gastwirth, J.L., Rubin, H.: Effect of dependence on the level of some one-sample tests. J. Am. Stat. Assoc. 66(336), 816–820 (1971)
Gel, Y.R., Miao, W., Gastwirth, J.L.: The effect of dependence between observations on the proper interpretation of statistical evidence. Law Probab. Risk 8(1), 25–38 (2009)
Good, P.I., Hardin, J.W.: Common Errors in Statistics (and How to Avoid Them). Wiley, Hoboken (2012)
Greenewald, K., Zhou, S., Hero, A., III.: Tensor graphical lasso (Teralasso). J. Roy. Stat. Soc. Ser. B (Stat. Methodol.) 81(5), 901–931 (2019)
Han, R., Willett, R., Zhang, A.R.: An optimal statistical and computational framework for generalized tensor estimation. Ann. Stat. 50(1), 1–29 (2022)
Hodoshima, J., Otsuki, N.: Evaluation by the Aumann and Serrano performance index and sharpe ratio: bitcoin performance. Appl. Econ. 51, 4282–4298 (2019). https://doi.org/10.1080/00036846.2019.1591601
Data source. https://www.cryptodatadownload.com/
Kalayci, C.B., Ertenlice, O., Akbay, M.A.: A comprehensive review of deterministic models and applications for mean-variance portfolio optimization. Expert Syst. Appl. 125, 345–368 (2019)
Khare, K., Oh, S.Y., Rajaratnam, B.: A convex pseudolikelihood framework for high dimensional partial correlation estimation with convergence guarantees. J. Roy. Stat. Soc. Ser. B Stat. Methodol. 803–825 (2015)
Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM Rev. 51(3), 455–500 (2009)
Korkusuz, B., Kambouroudis, D., McMillan, D.G.: Do extreme range estimators improve realized volatility forecasts? Evidence from G7 stock markets. Finan. Res. Lett. 103992 (2023)
Madasu, P., Teja, P.S.: Return-based vs. range-based volatility estimations–an overview. Int. J. Anal. Exp. Modal Anal. 11 (2019)
Markowitz, H.: Portfolio selection. J. Finan. 7, 77–91 (1952)
Mazanec, J.: Portfolio optimalization on digital currency market. J. Risk Financ. Manag. 14(4), 160 (2021). https://doi.org/10.3390/jrfm14040160
Olesen, J.L., Ianus, A., Østergaard, L., Shemesh, N., Jespersen, S.N.: Tensor denoising of multidimensional MRI data. Magn. Reson. Med. 89(3), 1160–1172 (2023)
Petropoulos, F., et al.: Forecasting: theory and practice. Int. J. Forecast. 38(3), 705–871 (2022)
Poythress, J., Ahn, J., Park, C.: Low-rank, orthogonally decomposable tensor regression with application to visual stimulus decoding of fMRI data. J. Comput. Graph. Stat. 31(1), 190–203 (2022)
Rubinstein, M.: Markowitz’s portfolio selection: a fifty-year retrospective. J. Financ. 57(3), 1041–1045 (2002)
Shah, D., Yu, C.L.: Iterative collaborative filtering for sparse noisy tensor estimation. In: 2019 IEEE International Symposium on Information Theory (ISIT), pp. 41–45. IEEE (2019)
Trautman, L.J., Foster, L.D., II.: The FTX crypto debacle: largest fraud since madoff? Univ. Memphis Law Rev. 54, 289 (2022). https://doi.org/10.2139/ssrn.4290093
Tsiligkaridis, T., Hero, A.O., III., Zhou, S.: On convergence of kronecker graphical lasso algorithms. IEEE Trans. Signal Process. 61(7), 1743–1755 (2013). https://doi.org/10.1109/tsp.2013.2240157
Wang, Y., Jang, B., Hero, A.: The sylvester graphical lasso (syglasso). In: International Conference on Artificial Intelligence and Statistics, pp. 1943–1953. PMLR (2020)
Zhu, Y., Cribben, I.: Sparse graphical models for functional connectivity networks: best methods and the autocorrelation issue. Brain Connect. 8(3), 139–165 (2018)
Acknowledgement
This work was supported by grants NASA AIST grant 21-AIST21 2-0059 and ONR grant N00014-21-1-2530. Also, the paper is based upon work supported by (while Y.R.G. was serving at) the NSF. The views expressed in the article do not necessarily represent the views of NASA, NSF or ONR. The work of I. C. was supported by the Natural Sciences and Engineering Research Council (Canada) grant RGPIN-2024-06102 and the Xerox Faculty Fellowship, Alberta School of Business. The work of D.O.B was supported by the 0012AA FEA Faculty Enhancement Awards at Portland State University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ofori-Boateng, D., Goel, J., Cribben, I., Gel, Y.R. (2024). Graphical Model-Based Lasso for Weakly Dependent Time Series of Tensors. In: Bifet, A., Davis, J., Krilavičius, T., Kull, M., Ntoutsi, E., Žliobaitė, I. (eds) Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2024. Lecture Notes in Computer Science(), vol 14945. Springer, Cham. https://doi.org/10.1007/978-3-031-70362-1_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-70362-1_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-70361-4
Online ISBN: 978-3-031-70362-1
eBook Packages: Computer ScienceComputer Science (R0)